Top-down model fitting for hand pose recovery in sequences of depth images
作者：
Highlights：
• A top-down strategy for hand pose recovery in depth images proposed
• Firstly, nearest shapes are extracted based on a new shape descriptor.
• Hand fingers are segmented and palm is extracted based on kNN shapes.
• Finger models are fitted to the hand given palm and finger segments.
• A previously trained bilinear temporal model is fitted to refine occluded joints.
摘要
•A top-down strategy for hand pose recovery in depth images proposed•Firstly, nearest shapes are extracted based on a new shape descriptor.•Hand fingers are segmented and palm is extracted based on kNN shapes.•Finger models are fitted to the hand given palm and finger segments.•A previously trained bilinear temporal model is fitted to refine occluded joints.
论文关键词：Hand pose recovery,Shape description,Depth image,Hand segmentation,Temporal modeling
论文评审过程：Received 9 October 2017, Revised 18 May 2018, Accepted 12 September 2018, Available online 21 September 2018, Version of Record 6 October 2018.
论文官网地址：https://doi.org/10.1016/j.imavis.2018.09.006
